Update README.md
Browse files
README.md
CHANGED
|
@@ -29,8 +29,12 @@ Presenting the **first INT4 quantized version** of [Cube3D v0.5](https://hugging
|
|
| 29 |
|
| 30 |
> 💡 The 44% VRAM reduction means this model now fits on a single 16 GB GPU (e.g. NVIDIA L4, A10 etc.), bringing high-quality text-to-3D generation to individual researchers and end-user hardware.
|
| 31 |
|
|
|
|
|
|
|
| 32 |
|
|
|
|
| 33 |
|
|
|
|
| 34 |
|
| 35 |
|
| 36 |
|
|
|
|
| 29 |
|
| 30 |
> 💡 The 44% VRAM reduction means this model now fits on a single 16 GB GPU (e.g. NVIDIA L4, A10 etc.), bringing high-quality text-to-3D generation to individual researchers and end-user hardware.
|
| 31 |
|
| 32 |
+
### Original BF16 vs Quantized INT4 Comparisons:
|
| 33 |
+
##### A. Easy Categories (7)
|
| 34 |
|
| 35 |
+
##### B. Medium Categories (6)
|
| 36 |
|
| 37 |
+
##### C. Complex Categories (2)
|
| 38 |
|
| 39 |
|
| 40 |
|